- Machine Learning
The intrinsic competitive nature of the fast-moving consumer goods (FMCG) industry have made it a priority for companies to maximize profitability by aggressive cost-cutting measures in the context of growing material cost, surging labor expenses and increasing demand for product customization. While exploring optimization opportunities in outbound logistics management, which mainly focuses on delivering goods and services out of a business entity, many market players shifted gears to delve into inbound logistics operations, which center on the management of materials and finished goods into a facility. This project unlocks cost saving opportunities in the inbound logistics system of a consumer goods company by answering two questions: What is the optimal minimum production quantity for finished goods? What is the appropriate minimum order quantity for packaging materials to minimize delivery and storage cost? Multiple machine learning techniques are utilized throughout the research: clustering techniques are used to identify MPQ, and a cost minimization model in Microsoft Excel and Python is developed to compare current cost with simulated cost. It is estimated that 16% cost savings can be obtained by optimizing MPQ and MOQ. Additionally, the models are highly replicable to other manufacturing sites of the CPG company to generate greater operational efficiency.